A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination
Recommendations for prioritizing COVID-19 vaccination have focused on the elderly at higher risk for severe disease. Existing models for identifying higher-risk individuals lack the needed integration of socio-demographic and clinical risk factors. Using multivariate logistic regression and random f...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/10/11/1185 |
| _version_ | 1797511162792771584 |
|---|---|
| author | Bettina Experton Hassan A. Tetteh Nicole Lurie Peter Walker Adrien Elena Christopher S. Hein Blake Schwendiman Justin L. Vincent Christopher R. Burrow |
| author_facet | Bettina Experton Hassan A. Tetteh Nicole Lurie Peter Walker Adrien Elena Christopher S. Hein Blake Schwendiman Justin L. Vincent Christopher R. Burrow |
| author_sort | Bettina Experton |
| collection | DOAJ |
| description | Recommendations for prioritizing COVID-19 vaccination have focused on the elderly at higher risk for severe disease. Existing models for identifying higher-risk individuals lack the needed integration of socio-demographic and clinical risk factors. Using multivariate logistic regression and random forest modeling, we developed a predictive model of severe COVID-19 using clinical data from Medicare claims for 16 million Medicare beneficiaries and socio-economic data from the CDC Social Vulnerability Index. Predicted individual probabilities of COVID-19 hospitalization were then calculated for population risk stratification and vaccine prioritization and mapping. The leading COVID-19 hospitalization risk factors were non-white ethnicity, end-stage renal disease, advanced age, prior hospitalization, leukemia, morbid obesity, chronic kidney disease, lung cancer, chronic liver disease, pulmonary fibrosis or pulmonary hypertension, and chemotherapy. However, previously reported risk factors such as chronic obstructive pulmonary disease and diabetes conferred modest hospitalization risk. Among all social vulnerability factors, residence in a low-income zip code was the only risk factor independently predicting hospitalization. This multifactor risk model and its population risk dashboard can be used to optimize COVID-19 vaccine allocation in the higher-risk Medicare population. |
| first_indexed | 2024-03-10T05:41:32Z |
| format | Article |
| id | doaj.art-b58120ecdab64cd9a0786d9ace1323c4 |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-10T05:41:32Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-b58120ecdab64cd9a0786d9ace1323c42023-11-22T22:28:38ZengMDPI AGBiology2079-77372021-11-011011118510.3390/biology10111185A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 VaccinationBettina Experton0Hassan A. Tetteh1Nicole Lurie2Peter Walker3Adrien Elena4Christopher S. Hein5Blake Schwendiman6Justin L. Vincent7Christopher R. Burrow8Humetrix Inc., Del Mar, CA 90214, USAWarfighter Health Mission Team, Department of Defense Joint Artificial Intelligence Center (JAIC), Arlington, VA 22202, USACoalition for Epidemic Preparedness Innovation (CEPI), Washington, DC 20006, USAUS Navy, Washington, DC 20376, USAHumetrix Inc., Del Mar, CA 90214, USAHumetrix Inc., Del Mar, CA 90214, USAHumetrix Inc., Del Mar, CA 90214, USAAmazon Web Services Inc., Seattle, WA 98109, USAHumetrix Inc., Del Mar, CA 90214, USARecommendations for prioritizing COVID-19 vaccination have focused on the elderly at higher risk for severe disease. Existing models for identifying higher-risk individuals lack the needed integration of socio-demographic and clinical risk factors. Using multivariate logistic regression and random forest modeling, we developed a predictive model of severe COVID-19 using clinical data from Medicare claims for 16 million Medicare beneficiaries and socio-economic data from the CDC Social Vulnerability Index. Predicted individual probabilities of COVID-19 hospitalization were then calculated for population risk stratification and vaccine prioritization and mapping. The leading COVID-19 hospitalization risk factors were non-white ethnicity, end-stage renal disease, advanced age, prior hospitalization, leukemia, morbid obesity, chronic kidney disease, lung cancer, chronic liver disease, pulmonary fibrosis or pulmonary hypertension, and chemotherapy. However, previously reported risk factors such as chronic obstructive pulmonary disease and diabetes conferred modest hospitalization risk. Among all social vulnerability factors, residence in a low-income zip code was the only risk factor independently predicting hospitalization. This multifactor risk model and its population risk dashboard can be used to optimize COVID-19 vaccine allocation in the higher-risk Medicare population.https://www.mdpi.com/2079-7737/10/11/1185COVID-19 vaccine prioritizationCOVID-19 booster vaccinesevere COVID-19 diseaserisk for severe COVID-19 infectionCOVID-19 vaccine booster prioritizationMedicare population |
| spellingShingle | Bettina Experton Hassan A. Tetteh Nicole Lurie Peter Walker Adrien Elena Christopher S. Hein Blake Schwendiman Justin L. Vincent Christopher R. Burrow A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination Biology COVID-19 vaccine prioritization COVID-19 booster vaccine severe COVID-19 disease risk for severe COVID-19 infection COVID-19 vaccine booster prioritization Medicare population |
| title | A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination |
| title_full | A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination |
| title_fullStr | A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination |
| title_full_unstemmed | A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination |
| title_short | A Predictive Model for Severe COVID-19 in the Medicare Population: A Tool for Prioritizing Primary and Booster COVID-19 Vaccination |
| title_sort | predictive model for severe covid 19 in the medicare population a tool for prioritizing primary and booster covid 19 vaccination |
| topic | COVID-19 vaccine prioritization COVID-19 booster vaccine severe COVID-19 disease risk for severe COVID-19 infection COVID-19 vaccine booster prioritization Medicare population |
| url | https://www.mdpi.com/2079-7737/10/11/1185 |
| work_keys_str_mv | AT bettinaexperton apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT hassanatetteh apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT nicolelurie apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT peterwalker apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT adrienelena apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT christophershein apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT blakeschwendiman apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT justinlvincent apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT christopherrburrow apredictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT bettinaexperton predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT hassanatetteh predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT nicolelurie predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT peterwalker predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT adrienelena predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT christophershein predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT blakeschwendiman predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT justinlvincent predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination AT christopherrburrow predictivemodelforseverecovid19inthemedicarepopulationatoolforprioritizingprimaryandboostercovid19vaccination |